Continual Learning in Transition

• URL: http://arxiv.org/abs/2608.06216v2
• Date: Wed, 12 Aug 2026 04:11:22 GMT
• Title: Continual Learning in Transition
• Abstract summary: Classical continual learning has primarily focused on enabling models to update and retain knowledge through parameter-centric mechanisms.<n>Emerging paradigms are reshaping the scope of CL beyond this traditional model adaptation view.<n>We examine the evolution of continual learning through three dimensions: When, How, and Where learning occurs.
• Score: 77.0733079568852
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Classical continual learning (CL) has primarily focused on enabling models to update and retain knowledge through parameter-centric mechanisms, e.g., training strategies, architectural designs, and weight adaptation. However, emerging paradigms are reshaping the scope of CL beyond this traditional model adaptation view. For instance, on-policy learning broadens the space of update mechanisms; test-time training extends CL from the training phase to inference; and external harness components such as memory, skill libraries, and interaction protocols extend the evolutionary boundaries of model capabilities far beyond the static parameter space. Collectively, these developments indicate a transition from parameter-centric learning toward system-level adaptation. To characterize this transition, we examine the evolution of continual learning through three dimensions: When, How, and Where learning occurs. The How dimension encompasses off-policy, on-policy, and beyond-gradient optimization mechanics. The When dimension captures evolution across pre-training, post-training, and inference-time stages. The Where dimension delineates updates occurring within internal parameters versus external structural constraints. Anchored by this tri-axial framework, we systematically survey representative methods, trace the ongoing transition of continual learning, and discuss the key challenges, broader implications, and future directions arising from this paradigm shift.

Related papers

• On the Importance of Gating: Memorization vs. In-Context Learning in State Space Models [50.824624057327725]
  State Space Models (SSMs) have emerged as a compelling alternative to Transformers.<n>We show through theory and experiments that this gating mechanism causes SSMs to first learn an in-weights "memorization" solution.<n>On the other hand, we find that gating is often beneficial for improving generalization to long sequence lengths.
  arXiv  Detail & Related papers  (2026-09-15T02:36:13Z)
• Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training [59.49057547517285]
  We systematically track the structural evolution of Transformer circuits throughout the supervised fine-tuning process.<n>Our empirical results reveal that circuits inherently exhibit "Free Evolution" during parameter updates.<n>This work underscores the necessity of "foresight" in mechanistic localization and proposes a framework for future research.
  arXiv  Detail & Related papers  (2026-05-07T11:59:52Z)
• Frame perspectives for process matrices: from coordinate parametrization to spacetime representation [0.0]
  We study how to implement and transform frame perspectives for quantum processes in the process-matrix formalism.<n>We show that unitary transformations can also be achieved in a different way, namely by extending the process with subsystems that define quantum reference frames.
  arXiv  Detail & Related papers  (2026-04-03T08:39:58Z)
• Deriving Hyperparameter Scaling Laws via Modern Optimization Theory [55.63126290312615]
  We study modern first-order boundss for methods based on the Linear Minimization Oracle (LMO)<n>Treating bounds in recent literature as a proxy and minimizing them across different tuning regimes yields closed-form power-law schedules for learning rate, momentum, and batch size.<n>Our results draw particular attention to the interaction between momentum and batch-size scaling, suggesting that optimal performance may be achieved with several scaling strategies.
  arXiv  Detail & Related papers  (2026-03-16T22:21:27Z)
• Continual Learning in Large Language Models: Methods, Challenges, and Opportunities [39.68332777229783]
  Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks.<n>This survey presents a comprehensive overview of CL methodologies tailored for LLMs, structured around three core training stages: continual pre-training, continual fine-tuning, and continual alignment.
  arXiv  Detail & Related papers  (2026-03-13T05:01:25Z)
• Teleodynamic Learning a new Paradigm For Interpretable AI [0.0]
  We introduce Teleodynamic Learning, a new paradigm for machine learning in which learning is not a fixed objective.<n>Inspired by living systems, this framework treats intelligence as the coupled evolution of three quantities.<n>We instantiate the framework in the Distinction Engine (DE11), a teleodynamic learner grounded in Spencer-Brown's Laws of Form.
  arXiv  Detail & Related papers  (2026-03-11T22:43:10Z)
• Modular Memory is the Key to Continual Learning Agents [100.09688599754465]
  We argue that combining the strengths of In-Weight Learning (IWL) and the newly emerged capabilities of In-Context Learning (ICL) through the design of modular memory is the missing piece for continual adaptation at scale.<n>We outline a conceptual framework for modular memory-centric architectures that leverage ICL for rapid adaptation and knowledge accumulation, and IWL for stable updates to model capabilities.
  arXiv  Detail & Related papers  (2026-03-02T11:40:05Z)
• Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks [3.924071936547547]
  Gated neural networks (RNNs) implicitly induce adaptive learning-rate behavior.<n>Effect arises from the coupling between state-space time scales--parametrized by the gates--and parameter-space dynamics.<n> Empirical simulations corroborate these claims.
  arXiv  Detail & Related papers  (2025-08-16T18:19:34Z)
• Network Dynamics-Based Framework for Understanding Deep Neural Networks [8.376259475051974]
  We propose a theoretical framework to analyze learning dynamics through the lens of dynamical systems theory.<n>We redefine the notions of linearity and nonlinearity in neural networks by introducing two fundamental transformation units at the neuron level.<n>Different transformation modes lead to distinct collective behaviors in weight vector organization, different modes of information extraction, and the emergence of qualitatively different learning phases.
  arXiv  Detail & Related papers  (2025-01-05T04:23:21Z)
• Continual Task Learning through Adaptive Policy Self-Composition [54.95680427960524]
  CompoFormer is a structure-based continual transformer model that adaptively composes previous policies via a meta-policy network. Our experiments reveal that CompoFormer outperforms conventional continual learning (CL) methods, particularly in longer task sequences.
  arXiv  Detail & Related papers  (2024-11-18T08:20:21Z)
• GEM: Group Enhanced Model for Learning Dynamical Control Systems [78.56159072162103]
  We build effective dynamical models that are amenable to sample-based learning. We show that learning the dynamics on a Lie algebra vector space is more effective than learning a direct state transition model. This work sheds light on a connection between learning of dynamics and Lie group properties, which opens doors for new research directions.
  arXiv  Detail & Related papers  (2021-04-07T01:08:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.